© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 5894
    Prev
    Next
    INDEX
    Explanations

    organizing or structuring information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Deleted
    0.72
    咐
    0.71
     உண்மைய
    0.69
    englisch
    0.67
    叱
    0.65
    TaskId
    0.64
    人に
    0.64
    ِلِّ
    0.62
     شدم
    0.62
    われた
    0.62
    POSITIVE LOGITS
     it
    1.00
     এটিকে
    0.72
     adsorbent
    0.68
     lever
    0.66
     dried
    0.66
     feedstock
    0.64
     reliance
    0.63
     ĝi
    0.63
     extrême
    0.62
     soigne
    0.62
    Activations Density 0.254%

    No Known Activations